AWS Certified Machine Learning Engineer Associate · Free Practice Question Medium
Question 22
An organization is deploying a machine learning model to edge devices with limited computing resources. They want to optimize the model to reduce resource usage without compromising accuracy. Which AWS service should they use to achieve this optimization?
-
A
Amazon SageMaker Real-Time Inference Endpoint
-
B
Amazon SageMaker Neo
-
C
AWS IoT Greengrass
-
D
Amazon SageMaker Batch Transform
Reveal correct answer
Correct answer: B
A.
Real-Time Inference Endpoints are for continuous, real-time predictions rather than model optimization for resource-constrained environments.
B.
Amazon SageMaker Neo is designed to optimize machine learning models for performance and efficiency across different hardware environments, including edge devices. It compiles models specifically for the target hardware, improving execution speed and reducing resource consumption without sacrificing model accuracy.
C.
AWS IoT Greengrass enables edge device deployment and management but does not optimize the model itself for resource efficiency.
D.
Batch Transform is intended for batch processing on large datasets and does not offer optimization for edge deployment.
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
